Toxicity
AI Risklanguage being rude, disrespectful, threatening, or identity-attacking toward certain groups of the user population (culture, race, and gender etc)
Overview
A source-backed snapshot of this AI risk.
Techniques0Attack methods connected to this risk.
Mitigations0Defenses that may help with related attacks.
Records2Source records unified into this concept.
Risk profile
How the MIT AI Risk Repository categorizes this risk.
Domain1. Discrimination & Toxicity
Subdomain1.2 > Exposure to toxic content
Entity2 - AI
Intent3 - Other; 2 - Unintentional
Timing2 - Post-deployment
CategorySocial Norm; Harmful Content
SubcategoryToxicity
Merged risk records
Source records unified into this canonical risk concept.
2 recordsView all →
MITRISK-Liu2024-30.06.01 - Toxicity
language being rude, disrespectful, threatening, or identity-attacking toward certain groups of the user population (culture, race, and gender etc)
MITRISK-Cui2024-02.01.02 - Toxicity
"Toxicity means the generated content contains rude, disrespectful, and even illegal information"
Mitigations
Defenses that may help with related attacks.
No propagated mitigations. No defense is available through the connected attack methods.
Source evidence
Research source for this risk, when available.
Included resource
Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment
Original source
MIT AI Risk Repository
Open the public repository used for AI risk records and taxonomy fields.